zlacker

[parent] [thread] 7 comments
1. halfli+(OP)[view] [source] 2023-09-12 18:38:22
I don't think translation is a great use case for ChatGPT and LLAMA. These models are overwhelmingly trained on English, and LLAMA2 which should have more data from other languages is still focused on languages w/ Latin/Cyrillic characters (so won't work well for Arabic, Hebrew, or CJK languages).

You're better off using models specialized in translation; General purpose LLMs are more useful when fine-tuning on specific tasks (some form of extraction, summarization, generative tasks, etc.), or for general chatbot-like uses.

replies(3): >>daniel+3c >>famous+XB >>achile+DI
2. daniel+3c[view] [source] 2023-09-12 19:15:16
>>halfli+(OP)
what models would you use for translation? I am working on a language learning tutor (trytutor.app, very early) and GPT-3.5 turbo has been working fine, for the most part.

For foreign language corrections ("correct this German sentence and give a reason for the correction"), GPT-3.5 doesn't quite have the horsepower so I use GPT-4

3. famous+XB[view] [source] 2023-09-12 20:44:02
>>halfli+(OP)
>You're better off using models specialized in translation

For a couple dozen languages, GPT-4 is by far the best translator you can get your hand on so basically no.

replies(2): >>daniel+jI >>two_in+Ad5
◧◩
4. daniel+jI[view] [source] [discussion] 2023-09-12 21:08:23
>>famous+XB
I will say that GPT-4 is just incredibly expensive. For my app I only use it for advanced translations/corrections, and usually a combination of GPT-3.5+Wiktionary is able to get the more simple stuff done
replies(1): >>all2+bT
5. achile+DI[view] [source] 2023-09-12 21:09:08
>>halfli+(OP)
There are plenty of examples in the literature of using LLMs for translation beating the metrics of non-LLM models, even for languages for which there isn't a lot of data. Transliterating non-Latin characters helps a lot with accuracy as well.
◧◩◪
6. all2+bT[view] [source] [discussion] 2023-09-12 21:53:53
>>daniel+jI
> GPT-3.5+Wiktionary

Can you share more about your app and what you're doing?

replies(1): >>daniel+XX
◧◩◪◨
7. daniel+XX[view] [source] [discussion] 2023-09-12 22:18:41
>>all2+bT
Sure! I'm building a personalized AI language learning tutor using Open AI's API and ElevenLabs (for Text to Speech).

Right now it's basically a chat bot that you can use to practice conversing with. It provides corrections for the things you type. Eventually I'd like to try adding Whisper as well to allow users to speak out loud.

When you hover over a word, you get a translation. Initially I thought using Open AI for every word translation would be too much, but I've been able to get it down to ~36-40 tokens/request. (3-4 cents/1000 requests). I also began parsing and uploading some of this [Wiktionary data](https://kaikki.org/dictionary/rawdata.html) and am working on a feature that integrates the GPT-3.5 translation with this Wiktionary data.

A lot of these features are still in the works but you can feel free to try it if you like (https://trytutor.app).

◧◩
8. two_in+Ad5[view] [source] [discussion] 2023-09-14 06:34:45
>>famous+XB
What would be the best local standalone solution for translation model? Personal use, mostly self-education. 2 popular languages both ways (like en-spa, fr-ger). Free, pretrained off the github would be the best. I can try and train say 100M params LLM on 4090 RTX. But I'm not sure satisfactory result are achievable.
[go to top]